A distributed denial of service (DDoS) attack is where one or more computers attack or target a server computer, by flooding internet traffic to the server. As a result, the server cannot be accessed by legitimate users. A result of this attack causes enormous losses for a company because it can reduce the level of user trust, and reduce the company’s reputation to lose customers due to downtime. One of the services at the application layer that can be accessed by users is a web-based lightweight directory access protocol (LDAP) service that can provide safe and easy services to access directory applications. We used a deep learning approach to detect DDoS attacks on the CICDDoS 2019 dataset on a complex computer network at the application layer to get fast and accurate results for dealing with unbalanced data. Based on the results obtained, it is observed that DDoS attack detection using a deep learning approach on imbalanced data performs better when implemented using synthetic minority oversampling technique (SMOTE) method for binary classes. On the other hand, the proposed deep learning approach performs better for detecting DDoS attacks in multiclass when implemented using the adaptive synthetic (ADASYN) method.

High quality palm oil is critical in ensuring Malaysia’s competitiveness in the sector. Studies have shown that there is a significant relationship between the quality of palm oil produced and the ripeness of the fruits used in producing the oil. Correct ripeness of the fresh fruit bunches (FFB) produces higher quality and more oil content. Unripe FFB produces the least oil and overripe FFB produces oil of lower quality. According to Malaysian Palm Oil Board (MPOB), the main factors that determine the ripeness of the oil palm FFB are its colour and the number of its loose fruits. To classify the ripeness according to these two factors, there are 3 common techniques has been implemented in the previous work which are; colour feature extraction, texture feature extraction and Deep Learning method. To handle fruit ripeness classification problem, this paper provides a short review to the reader to grasp the applicable technique that can be implemented.

In recent manufacturing industry, improving the manufacturing process is of paramount importance. One area that holds great potential for enhancement is the application and manipulation of maintenance data. By effectively leveraging this data, manufacturers can optimize maintenance schedules, leading to increased efficiency, reduced costs, and minimized downtime. However, the challenge lies in handling vast amounts of maintenance data that often come in various formats, making it difficult to extract valuable insights. Without proper analysis, this unprocessed data can result in unforeseen issues, costly disruptions, and extended downtime periods. To overcome this obstacle, modern manufacturing companies are turning to advanced technologies such as language modelling, text classification, machine translation, and Named Entity Recognition (NER). To the best of our knowledge, no investigation has been conducted to assess the impact of text preprocessing on NER performance. Improving the initial stage of NER, such as text preprocessing, can enhance NER performance which leads to the training model’s efficiency performance. In this study, Hidden Markov Model (HMM) is employed to improve NER performance by utilizing oversampling and text preprocessing techniques. The study is performed without IOB labelling and consider seven specific entities and the preprocessing text tasks include tokenization, lemmatization, erase punctuation, stop words removal, and elimination of long and short words. As a result, HMM for NER with oversampling and preprocessed text outperformed the one without any of both by 20.10% and 27.59%, respectively, due to consideration of significant classes and words among the entity classes in preprocessed factory reports. This finding highlights the importance of text preprocessing method selection in NER and its capability to optimize maintenance schedule and reduce downtime.

Handwriting recognition is an important research area in the domains of computer vision (CV), pattern recognition, and Natural Language Processing (NLP). Accurate recognition of handwritten text has numerous applications, including digitizing historical documents, automating data entry, and document analysis or verification. Handwriting recognition has been researched widely and applied to the scripts of various languages including Latin, Chinese, Hindi, and Arabic. This study focuses on offline handwritten Arabic text recognition (HATR), addressing the unique challenges posed by Arabic, which is a language spoken widely across the globe. Handwritten Arabic text poses significant challenges in handwriting recognition because of its cursive nature, rich calligraphic styles and varied diacritics. Hence, various methods have been explored to address these challenges and complexities. This paper presents a comprehensive study of the research advances in offline HATR. It includes review of the background, challenges, the strengths of methods proposed in the literature, the solutions offered, as well as highlights the weaknesses of each technique and finally, future research direction.

Imbalanced data handling in multiclass distributed denial of service attack detection using deep learning

Quantifying finger strength during Activities of daily living (ADLs) and the improvements observed in individuals undergoing physical therapy due to stroke or arthritis can provide valuable insights into hand function. The developed real-time IoT-based glove for finger strength monitoring is an instrumented device that incorporates Internet of Things technology. This includes utilizing an ESP8266 Wi-Fi module to connect to the selected IoT analytics platform, Blynk, and an Arduino microcontroller as the main control unit. The glove features a 16x2 LCD display to present the user's pinch strength values for the thumb and index finger. Force-sensitive resistor (FSR) sensors were employed to assess this parameter. The measured strength values were initially displayed on the LCD and then transmitted to a Blynk server for real-time graphical representation. The effectiveness of the designed glove was evaluated through participant testing, where individuals wore the glove and performed pinching tasks. Comparisons were made between the pinch strength readings from the instrumented glove and a traditional pinch meter. The sensing results demonstrated a promising degree of accuracy, with a minimum and highest average mean percentage error of 8.23% and 14.08%, respectively. The developed IoT-based pinch strength monitoring glove have the potential to enable physiotherapists to quantitatively evaluate progress in patient pinch strength during object manipulation tasks requiring pinching. Furthermore, the success of rehabilitation programs can also be assessed using this system.